OceanBase Database supports vector data storage, vector indexes, and embedding vector retrieval in V4.3.3 and later. You can store vectorized data in OceanBase Database for further retrieval.
LangChain is a framework for developing language model-driven applications. It enables an application to have the following capabilities:
Context awareness: The application can connect language models to context sources, such as prompt instructions, a few examples, and content requiring responses.
Reasoning: The application can perform reasoning based on language models. For example, it can decide how to answer a question or what actions to take based on the provided context.
This topic describes how to integrate the vector retrieval feature of OceanBase Cloud, Tongyi Qianwen (Qwen), and LangChain for Document Question Answering (DQA).
Prerequisites
A transactional cluster instance of the MySQL compatible mode is available in your environment.
To use a cluster instance, you first need to create a tenant by referring to Create a tenant.
You have created a MySQL-compatible tenant, a database, and an account, and granted the read and write permissions to the database account. For more information, see Create an account and Create a database (MySQL compatible mode).
You have been granted the project admin or instance admin role to perform read and write operations on instances in the project. If you do not have the required permissions, contact the organization admin.
You have installed Python 3.9 or later and pip. If Python installed on your server is of an early version, you can use Miniconda to build a new environment of Python 3.9 or later. For more information, see Installing Miniconda.
You have installed Poetry, Pyobvector, and DashScope. The installation commands are as follows:
python3 -m pip install poetry python3 -m pip install pyobvector python3 -m pip install dashscopeYou have installed LangChain. The installation command is as follows:
python3 -m pip install langchain
Step 1: Obtain the database connection information
Log in to the OceanBase Cloud console.
In the instance list page, expand the the information of the target instance.
Select Connect > Get Connection String under the target tenant.
In the pop-up window, select Public Network as the connection method.
Follow the prompts in the pop-up window to obtain the public endpoint and the connection string.
Step 2: Register an LLM account
Register an Alibaba Cloud Model Studio account, activate the model service, and obtain an API key.
Notice
-
The Qwen large language model (LLM) provides a free quota. Charges will be incurred after the free quota is used up.
Specify the API key for the relevant environment variable.
export DASHSCOPE_API_KEY="YOUR_DASHSCOPE_API_KEY"
Step 3: Build an AI assistant
Clone the relevant code repository for third-party integration on GitHub
git clone -b obvec https://github.com/GITHUBear/langchain.git
cd langchain/libs/community
Load and split a document
The project contains sample data, which is stored in ./../docs/docs/how_to/state_of_the_union.txt. Use CharacterTextSplitter to split the document of sample data into blocks, with each block containing about 1,000 characters.
from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings import DashScopeEmbeddings
from langchain_community.vectorstores import OceanBase
from langchain_text_splitters import CharacterTextSplitter
import os
DASHSCOPE_API = os.environ.get("DASHSCOPE_API_KEY", "")
embeddings = DashScopeEmbeddings(
model="text-embedding-v1", dashscope_api_key=DASHSCOPE_API
)
loader = TextLoader("../../docs/docs/how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
Insert the data into OceanBase Cloud
connection_args = {
"host": "127.0.0.1",
"port": "2881",
"user": "root@test",
"password": "",
"db_name": "test",
}
DEMO_TABLE_NAME = "demo_ann"
ob = OceanBase(
embedding_function=embeddings,
table_name=DEMO_TABLE_NAME,
connection_args=connection_args,
drop_old=True,
normalize=True,
)
res = ob.add_documents(documents=docs)
Perform vector search
Here is an example of searching for "What did the president say about Ketanji Brown Jackson" from state_of_the_union.txt:
query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = ob.similarity_search_with_score(query, k=3)
for doc, score in docs_with_score:
print("-" * 80)
print("Score: ", score)
print(doc.page_content)
print("-" * 80)
The expected output is as follows:
--------------------------------------------------------------------------------
Score: 1.204783671324283
Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections.
Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.
One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.
And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
Score: 1.2146663629717394
It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world—particularly with China.
As I’ve told Xi Jinping, it is never a good bet to bet against the American people.
We’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America.
And we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice.
We’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities.
4,000 projects have already been announced.
And tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair.
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
Score: 1.2193955178945004
Vice President Harris and I ran for office with a new economic vision for America.
Invest in America. Educate Americans. Grow the workforce. Build the economy from the bottom up
and the middle out, not from the top down.
Because we know that when the middle class grows, the poor have a ladder up and the wealthy do very well.
America used to have the best roads, bridges, and airports on Earth.
Now our infrastructure is ranked 13th in the world.
We won’t be able to compete for the jobs of the 21st Century if we don’t fix that.
That’s why it was so important to pass the Bipartisan Infrastructure Law—the most sweeping investment to rebuild America in history.
This was a bipartisan effort, and I want to thank the members of both parties who worked to make it happen.
We’re done talking about infrastructure weeks.
We’re going to have an infrastructure decade.
--------------------------------------------------------------------------------